Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific numerical terms or bullet point lists

    oai_token-act-pair · gpt-3.5-turbo

    places where formatting or special characters are used in documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pping
    -0.67
    tight
    -0.66
    itored
    -0.64
    onto
    -0.64
    Meanwhile
    -0.57
    dding
    -0.57
     jeopard
    -0.56
    emaker
    -0.56
     risking
    -0.56
    leground
    -0.55
    POSITIVE LOGITS
     screenshots
    0.94
     quotations
    0.91
     textures
    0.90
     poems
    0.90
     recipes
    0.90
     lyrics
    0.87
     translations
    0.87
     annotations
    0.85
     illustrations
    0.85
     quotes
    0.82
    Act Density 0.741%

    No Known Activations